The DOI matches its Crossref record; 56 of the 60 references it cites were found in a registry or an index.
Improving Computer-Aided Detection UsingConvolutional Neural Networks and Random View Aggregation
Open accessAbstract
Automated computer-aided detection (CADe) has been an important tool in clinical practice and research. State-of-the-art methods often show high sensitivities at the cost of high false-positives (FP) per patient rates. We design a two-tiered coarse-to-fine cascade framework that first operates a candidate generation system at sensitivities ∼ 100% of but at high FP levels. By leveraging existing CADe systems, coordinates of regions or volumes of interest (ROI or VOI) are generated and function as input for a second tier, which is our focus in this study. In this second stage, we generate 2D (two-dimensional) or 2.5D views via sampling through scale transformations, random translations and rotations. These random views are used to train deep convolutional neural network (ConvNet) classifiers. In testing, the ConvNets assign class (e.g., lesion, pathology) probabilities for a new set of random views that are then averaged to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. The methods are evaluated on three data sets: 59 patients for sclerotic metastasis detection, 176 patients for lymph node detection, and 1,186 patients for colonic polyp detection. Experimental results show the ability of ConvNets to generalize well to different medical imaging CADe applications and scale elegantly to various data sets. Our proposed methods improve performance markedly in all cases. Sensitivities improved from 57% to 70%, 43% to 77%, and 58% to 75% at 3 FPs per patient for sclerotic metastases, lymph nodes and colonic polyps, respectively.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“We obtain 86% sensitivity on 3 false positives (FP) per patient, versus the prior state-of-art sensitivities of 78% [36] (stacked shallow learning) and 70% [22] (CNN), as prior state-of-the-art.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [22]
In the citing paper
“GoogLeNet-RI-L | 0.95 | 0.85 | 0.91 | 0.69”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [22]
In the citing paper
“This difference lies in the fact that annotated lymph node segmentation masks are required to learn a mid-level semantic boundary detector [36], whereas CNN approaches only need LN locations for training [22].”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [22]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Potentially, larger and deeper convolutional neural networks could be applied to further improve classification performance [59], [60].”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 10×
“In order to increase the variation of the training data and to avoid overfitting analogous to the data augmentation approach in [14], [17] and [18], multiple 2D or 2.”
BackgroundMethodInfluentialGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 1×
“Potentially, larger and deeper convolutional neural networks could be applied to further improve classification performance [59], [60].”
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 1×
“This type of cascade classification is similar in spirit to our presented second tier deep classifier (ConvNet), but uses state-of-the-art shallow classifiers (libSVM [47] and sparse linear fusion via the Relevance Vector Machine [48]).”
ResultRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 1×
“Potentially allowing the ConvNet optimization to start from an initialization that is better than starting from Gaussian random parameters [57], [58].”
BackgroundBackpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 2×
“Balancing between positive and negative training populations is generally beneficial for training ConvNets when optimizing with logistic regression cost [15], [14].”
BackgroundMethodTwo-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756 · cited 3×
“Likewise, the compositional two-stream 2D ConvNet models run on separate spatial (RGB) and temporal (i.e., optical flow field) video frames and achieve the mean accuracy of 87.9% in action classification task, based on a middle scale dataset UCF-101 [50].”
BackgroundInfluentialImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · cited 1×
“It is a variation of the previously suggested “DropOut” method [29], [30].”
MethodLarge-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 1×
“This result significantly outperforms the direct 3D “spatial-temporal” ConvNet method [51] at 65.”
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“Potentially allowing the ConvNet optimization to start from an initialization that is better than starting from Gaussian random parameters [57], [58].”
Background
Flagged first, then by citations
4 of the 60 references couldn’t be matched to a known paper.
Research works printed but not linked: 6
- wan, 2013, Regularization of neural networks using DropConnect, Proc Int Conf Mach Learn
- organization, 2014, Cancer Fact Sheet
- park, 2015, Polyp detection in colonoscopy videos using deeply-learned hierarchical features, Seoul nat'l univ
- 10.1007/978-3-319-14104-6_16 · DOI
- ciresan, 2012, Deep neural networks segment neuronal membranes in electron microscopy images, Adv Neural Inf Process Syst, 2843
- seff, 2014, MICCAI, 544
Cited by
Sorted by citations
Items 301–400 of 545
Computer aided detection and diagnosis in medical imaging
Hernández‐Rodríguez, J., Fraile, F. J. C., Conde, M. J. R., & Llorente, P. L. G. (2016) · Ninth International Conference on Technological Ecosystems for Enhancing Multiculturality (TEEM'21) · doi:10.1145/3012430.3012567 · Cited by 37
“Deep learning neural networks have been applied to solve many problems [7,9].”
BackgroundMethodPointExplainer: Towards Transparent Parkinson's Disease Diagnosis
Wang, X.-C., Nõmm, S., Huang, J.-Q., Medijainen, K., Toomela, A., & Ruzhansky, M. (2025) · arXiv.org · doi:10.48550/arxiv.2505.03833 · Cited by 13
Skin lesion image classification method based on extension theory and deep learning
Bian, X.-F., Pan, H.-W., Zhang, K., Li, P., Li, J.-B., & Chen, C. (2022) · Multimedia tools and applications · doi:10.1007/s11042-022-12376-3 · Cited by 13
“Malignant melanoma is one of the most dangerous skin cancers [39].”
Background3D Deep Learning for Anatomical Structure Segmentation in Multiple Imaging Modalities
Villarini, B., Asaturyan, H. A., Kurugol, S., Afacan, O., Bell, J. D., & Thomas, E. (2021) · 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS) · doi:10.1109/cbms52027.2021.00066 · Cited by 13
An intelligent system of pelvic lymph node detection
Wang, H., Huang, H., Wang, J., Wei, M., Zhang, Y., Wang, Z., & Zhang, H. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22452 · Cited by 18
“However, only the purpose of Reference [30] is to detect lymph nodes, while 7,31,32 is based on the results of Reference [30] to reduce FP lymph node candidates.”
BackgroundMethodCalculating the target exposure index using a deep convolutional neural network and a rule base
Takaki, T., Murakami, S., Watanabe, R., Aoki, T., & Fujibuchi, T. (2020) · Physica Medica · doi:10.1016/j.ejmp.2020.02.012 · Cited by 14
Lü, L., Wang, D., Wang, L., Linning, E., Guo, P., Li, Z., Xiang, J., Yang, H., Li, H., Yin, S., et al. (2020) · European Radiology · doi:10.1007/s00330-020-06663-6 · Cited by 16
Self-citationDown syndrome prediction/screening model based on deep learning and illumina genotyping array
Feng, B., Samuels, D. C., Hoskins, W., Guo, Y., Zhang, Y., Tang, J., & Meng, Z.-B. (2017) · IEEE International Conference on Bioinformatics and Biomedicine · doi:10.1109/bibm.2017.8217674 · Cited by 13
“Next, we used the original Illumina genotyping array data with total 5458 SNP features to construct DS prediction/screening models using support vector machine (SVM), random forest, and decision tree algorithms.”
MethodInfluentialZhang, Z., Xing, F., Su, H., Shi, X., & Yang, L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.07281 · Cited by 14
“Deep learning has became the mainstream of medical image contour detection and segmentation methods [89, 222, 67, 189, 173, 10, 153, 18].”
BackgroundSelf-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis
Li, X., Zhong, A., Lin, M., Guo, N., Sun, M., Sitek, A., Ye, J., Thrall, J. H., & Li, Q. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67389-9_25 · Cited by 11
“Current solutions for addressing this issue [3] include traditional data augmentation techniques based on affine transformations to expand the labeled dataset [18, 19, 20].”
BackgroundThorax disease diagnosis using deep convolutional neural network
Chen, J., Qi, X., Tervonen, O. A., Sílven, O., Zhao, G., & Pietikäinen, M. (2016) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7591186 · Cited by 11
“[16] proposed to improve computer-aided detection using convolutional neural networks and random view aggregation.”
BackgroundConvolutional Neural Networks for Predictive Modeling of Lung Disease
Liang, Y., Liu, X.-Q., Xia, H., Cang, Y., Zheng, Z., & Yang, Y. (2024) · 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics62053.2024.10796475 · Cited by 12
“Roth et al. [16] used 2D CNN to detect lung nodules and reduce misjudgment through image preprocessing and feature extraction.”
COVID-19 Pneumonia Classification Based on NeuroWavelet Capsule Network
Monday, H. N., Li, J., Nneji, G. U., Nahar, S., Hossin, M. A., & Jackson, J. K. (2022) · Healthcare · doi:10.3390/healthcare10030422 · Cited by 13
Deep Learning Applications in Medical Image Analysis
Singha, A., Thakur, R. S., & Patel, T. (2021) · Wiley eBooks · doi:10.1002/9781119711278.ch11 · Cited by 47
Computer-Aided Detection of Lung Nodules in Chest X-Rays using Deep Convolutional Neural Networks
Uçar, M., & Uçar, E. (2019) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis.02.01.538249 · Cited by 17
“DCNN is also applied in many medical image processing tasks [8-12] recently.”
Malignancy characterization of hepatocellular carcinoma using hybrid texture and deep features
Wang, Q., Zhang, L., Xie, Y., Zheng, H., & Zhou, W. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8297066 · Cited by 11
“In order to increase the training sample for deep learning, a multiview resampling technique was performed within the 3D tumor region similar to the work in [9].”
MethodSaleh, M., Serte, S., Al-turjman, F., Abdulkadir, R. A., Sa', Z., Ameen, I., & Ozsoz, M. (2023) · International Journal of Nanotechnology · doi:10.1504/ijnt.2023.131109 · Cited by 12
Deep learning in mesoscale brain image analysis: A review
Chen, R., Liu, M., Chen, W., Wang, Y., & Meijering, E. H. W. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107617 · Cited by 13
Radiomics and artificial neural networks modelling for identification of high-risk carotid plaques
Gui, C., Cao, C. Y., Zhang, X., Zhang, J., Ni, G., & Ming, D. (2023) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2023.1173769 · Cited by 13
“Due to the limited amount of training data in our dataset, volumentations (19) techniques including “Random Rotation”, “Random Flip”, “Gaussian Blur”, “Gaussian Noise” and four combinations of static data augumentations were used to expand the dataset to sixty times the original dataset, which could also help the mode…”
MethodVideo Pretraining Advances 3D Deep Learning on Chest CT Tasks
Ke, A., Huang, S.-C., O'Connell, C., Klimont, M., Yeung, S., & Rajpurkar, P. (2023) · International Conference on Medical Imaging with Deep Learning · doi:10.48550/arxiv.2304.00546 · Cited by 11
“We then transferred these weights and finetuned them on RSNA for PE detection and LIDC for lung nodule detection. pretraining approach adapts 2D or 2.5D models to 3D tasks (Tajbakhsh et al., 2015; Roth et al., 2016).”
MethodMa, Y., Peng, Y., & Wu, T. (2022) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-219312 · Cited by 4
“Admittedly, the strategy depicted in [39, 40] paves one of the future ways to improve the proposed framework performance.”
Li, S., Xie, Y., Wang, G., Zhang, L., & Zhou, W. (2022) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2022.102050 · Cited by 10
Data Augmentation Techniques for Deep Learning-Based Medical Image Analyses
Kim, M., & Bae, H.-J. (2020) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2020.0158 · Cited by 16
“Numbers below images represent: [1] horizontal flip, [2] vertical flip, [3] elastic transform, [4] grid distort, [5] optical distort, [6] sharp, [7] motion blur, [8] gaussian blur, [9] rotation, [10] shift, [11] zoom, [12] crop, and [13] gamma correct.”
Zhu, Z., Yan, K., Jin, D., Cai, J., Ho, T., Harrison, A. P., Guo, D., Chao, C.-H., Ye, X., Xiao, J. Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.13705 · Cited by 11
“In contrast, [27,28] proposed a 2.5D patch-based convolutional neural network (CNN) with random view aggregation to classify LNs given all LN candidates already detected, and achieves SOTA classification accuracy for enlarged LNs.”
BackgroundMethodResultInfluentialSelf-citationFocal Loss Function based DeepLabv3+ for Pathological Lymph Node Segmentation on PET/CT
Xu, G., Cao, H., Dong, Y., Yue, C., Li, K., & Tong, Y. (2020) · International Conference on Intelligent Medicine and Image Processing (IMIP) · doi:10.1145/3399637.3399651 · Cited by 12
“Currently, most of the published papers [2][6][13][16] focus on detection or segmentation enlarged lymph nodes on CT images because of its high resolution.”
BackgroundKarimi, D., & Ruan, D. (2017) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-319-66179-7_45 · Cited by 11
“networks can achieve state of the art results in cancer detection and classification [2,8].”
BackgroundMethodTorabi, A., Jahromy, F. Z., & Daliri, M. R. (2017) · Cognitive Computation · doi:10.1007/s12559-017-9487-z · Cited by 9
“used in 2D and 3D medical-image analysis [35, 39].”
MethodAn Improved Nested U-Net Network for Fluorescence In Situ Hybridization Cell Image Segmentation
Jian, Z., Song, T., Zhang, Z., Ai, Z., Zhao, H., Tang, M., & Liu, K. (2024) · Sensors · doi:10.3390/s24030928 · Cited by 10
Verzat, C., Harley, J., Patani, R., & Luisier, R. (2021) · Neuropathology and Applied Neurobiology · doi:10.1111/nan.12770 · Cited by 10
Medical Image Retrieval Using Empirical Mode Decomposition with Deep Convolutional Neural Network
Zhang, S., Zhi, L., & Zhou, T. (2020) · BioMed Research International · doi:10.1155/2020/6687733 · Cited by 14
Hegde, N., Muralidhara, S., S., S., P., D., & Latte, M. (2020) · Current medical imaging · doi:10.2174/2213335607999200415141427 · Cited by 10
Li, Y., Huang, H., Zhang, L., Wang, G., Zhang, H., & Zhou, W. (2020) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi45749.2020.9098705 · Cited by 11
“One direct way is to extract deep feature by the utilization of 2D Convolutional neural network (CNN) based on orthogonal planes or Multiview aggregation for lesion characterization [5, 6].”
MethodWang, B., Liu, C., Chen, S., Dong, S., & Hu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2937993 · Cited by 14
“With the development of software and hardware in recent years, artificial neural network has regained attentions for significantly improving the performance ofmany intelligent processing tasks [16]–[24], such as image classification, speech recognition, object detection, face recognition, semantic separation, machine…”
MethodBi-stream CNN Down Syndrome screening model based on genotyping array
Feng, B. J., Hoskins, W., Zhang, Y., Meng, Z., Samuels, D. C., Wang, J., Xia, R., Liu, C., Tang, J., & Guo, Y. P. (2018) · BMC Medical Genomics · doi:10.1186/s12920-018-0416-0 · Cited by 16
Chen, Y., Ren, Y., Fu, L., Xiong, J., Larsson, R., Xu, X., Sun, J., & Zhao, J. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc.2018.8512305 · Cited by 10
“5D and generates polyp candidates in a traditional way [6].”
Wang, Z., Chetouani, A., & Jennane, R. (2023) · arXiv.org · doi:10.48550/arxiv.2302.13336 · Cited by 10
“…a fundamental component of artificial intelligence, has gained traction in the field of computer vision in recent years, particularly the use of Convolutional Neural Networks (CNNs) [9], which have effectively accomplished tasks such as detection [10], segmentation [11] and classification [12].”
Three Aspects on Using Convolutional Neural Networks for Computer-Aided Detection in Medical Imaging
Shin, H.-C., Roth, H. R., Gao, M., Lü, L., Xu, Z., Nogues, I., Yao, J., Mollura, D. J., & Summers, R. M. (2017) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-42999-1_8 · Cited by 10
Self-citationAgyekum, E. A., Yuzhi, Z., Yu, F., Agyekum, D. N., Wang, X., Issaka, E., Li, C., Shen, X., Qian, X., & Wu, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-05551-7 · Cited by 10
“This process ensures that the model focuses on identifying thyroid lesions amidst potential noise sources 24 .”
InfluentialAgyekum, E. A., Wang, Y., Issaka, E., Ren, Y., Tan, G., Shen, X., & Qian, X. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-02989-7 · Cited by 10
“Given the limited training data available in this study and the need to mitigate overfitting and sample imbalances, a method called data augmentation was employed [44, 45] (Fig.”
Linked Color Imaging with Artificial Intelligence Improves the Detection of Early Gastric Cancer
Zhao, Y., Dohi, O., Ishida, T., Yoshida, N., Ochiai, T., Mukai, H., Seya, M., Yamauchi, K., Miyazaki, H., Fukui, H., et al. (2024) · Digestive Diseases · doi:10.1159/000540728 · Cited by 11
“Convolutional neural networks (CNNs) are typical DL algorithms with multilayer perceptrons in convolutional layers for extracting features from input, and activation layers for converting values of feature maps from linear-related to non-linear-related values after convolutional fi ltering [11].”
Yu, Q.-J., Wang, Y.-R., Yan, K., Li, H.-S., Guo, D.-Z., Zhang, L., Lu, L., Shen, N., Wang, Q.-F., Ding, X.-W., et al. (2024) · European Conference on Computer Vision · doi:10.48550/arxiv.2404.03819 · Cited by 9
“Computer-aided detection (CADe) has been an active research area in medical image analysis for the past three decades, evolving rapidly in recent years when equipped with deep learning techniques [1, 10, 11, 39, 48].”
BackgroundSelf-citationPatterson, A., Elbasir, A., Tian, B., & Auslander, N. (2023) · Cancers · doi:10.3390/cancers15071958 · Cited by 8
“Although aggregation may reduce sparsity, care must be taken to ensure results are biologically interpretable [233,234].”
BackgroundA multi-task learning approach for chemical process abnormity locations and fault classifications
Zhao, W.-L., Li, J.-C., & Li, H.-G. (2022) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2022.104719 · Cited by 9
Lin, Q., Chen, X., Liu, L., Cao, Y., Man, Z., Zeng, X., & Huang, X. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac944d · Cited by 9
Patel, R. (2021) · arXiv.org · doi:10.48550/arxiv.2105.12564 · Cited by 9
“developed a two-tiered coarse-to-fine cascade architecture for a CAD device [5].”
Automatic Measurement of Pennation Angle from Ultrasound Images using Resnets
Zheng, W., Liu, S., Chai, Q.-W., Pan, J., & Chu, S. (2021) · Ultrasonic Imaging · doi:10.1177/0161734621989598 · Cited by 10
“17 Tissue organ segmentation is the key to quantitative evaluation of medical images.”
BackgroundDeep Learning Technology for Drunks Detection with Infrared Camera
Iamudomchai, P., Seelaso, P., Pattanasak, S., & Piyawattanametha, W. (2020) · 2020 6th International Conference on Engineering, Applied Sciences and Technology (ICEAST) · doi:10.1109/iceast50382.2020.9165395 · Cited by 9
“• Testing To classify an unseen image, we combine random-view aggregation and multiple crop testing [7] to produce the final prediction score.”
MethodClassification of Benign and Malignant Pulmonary Nodules Based on Deep Learning
Zhang, Y., Zhang, J., Zhao, L., Wei, X., & Zhang, Q. (2018) · International Conference on Information Science and Control Engineering · doi:10.1109/icisce.2018.00042 · Cited by 14
“Inspired by [19], we try to process the CT image and construct the 2.”
MethodJi, Z., Guo, D.-Z., Wang, P., Yan, K., Lu, L., Xu, M.-F., Zhou, J.-R., Wang, Q.-F., Ge, J., Gao, M., et al. (2023) · arXiv.org · doi:10.48550/arxiv.2302.00162 · Cited by 9
Self-citationDeep Learning for Medical Image Recognition: Open Issues and a Way to Forward
Nair, M. M., Kumari, S., Tyagi, A. K., & Sravanthi, K. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-15-9689-6_38 · Cited by 14
Liver lesion detection in CT using deep learning techniques
Ben-Cohen, A., & Greenspan, H. (2020) · doi:10.1016/b978-0-12-816176-0.00008-9 · Cited by 9
Supraspinatus extraction from MRI based on attention-dense spatial pyramid UNet network
Wang, P., Liu, Y., & Zhou, Z. (2024) · Journal of Orthopaedic Surgery and Research · doi:10.1186/s13018-023-04509-7 · Cited by 7
“DL methods have made significant contributions to medical imaging research, with representative works including brain tumor segmentation [21], lung nodule detection [22], and case image segmentation [23].”
MethodAdaptive kernel selection network with attention constraint for surgical instrument classification
Hou, Y., Zhang, W., Liu, Q., Ge, H., Meng, J., Zhang, Q., & Wei, X. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06368-x · Cited by 9
“Besides, medical image processing has also been applied to solve different medical tasks, including computer-aided detection (CADe) in radiological diagnoses [34], prostate image analysis based on 3D image segmentation [30], 3D MRI brain coronal slices image registration [3], detection of critical findings in head CT…”
MethodDeep learning for breast cancer classification: Enhanced tangent function
Thapa, A., Alsadoon, A., Prasad, P. W. C., Bajaj, S. K., Alsadoon, O. H., Rashid, T. A., Ali, R. S., & Jerew, O. D. (2021) · Computational Intelligence · doi:10.1111/coin.12476 · Cited by 8
“The accuracy can be increased by 2% when batch normalization is applied [14] and can be tested in this model in practice for its real validity.”
BackgroundKougia, V., Pavlopoulos, J., Papapetrou, P., & Gordon, M. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocab046 · Cited by 10
R2D2: A scalable deep learning toolkit for medical imaging segmentation
Guedria, S., Palma, N. D., Renard, F., & Vuillerme, N. (2020) · Software Practice and Experience · doi:10.1002/spe.2878 · Cited by 7
Mobile Phone based ensemble classification of Deep Learned Feature for Medical Image Analysis
Dittimi, T. V., & Suen, C. Y. (2019) · IETE Technical Review · doi:10.1080/02564602.2019.1576550 · Cited by 11
Yoshida, H., Näppi, J. J., & Hironaka, T. (2018) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.2293848 · Cited by 7
Double U-Nets for Image Segmentation by Integrating the Region and Boundary Information
Guo, W., Zhou, H., Gong, Z., & Zhang, G. (2021) · IEEE Access · doi:10.1109/access.2021.3075294 · Cited by 10
“To this end, some groups employed the affine transformation to generate samples and then used the generated samples to train their networks [10], [11].”
MethodEvolutionary GAN–Based Data Augmentation for Cardiac Magnetic Resonance Image
Fu, Y., Gong, M., Yang, G., Wei, H., & Zhou, J.-L. (2021) · Computers Materials & Continua · doi:10.32604/cmc.2021.016536 · Cited by 8
“The classical data augmentation techniques mainly include affine transformation methods such as image translation, rotation, scaling, flipping, and shearing [10,11].”
MethodMulti-Tasking U-Shaped Network for Benign and Malignant Classification of Breast Masses
Cao, H., Pu, S., Tan, W., Tong, J., & Zhang, D. (2020) · IEEE Access · doi:10.1109/access.2020.3042889 · Cited by 16
“Studies have shown that computer-aid diagnostic systems can provide fast and reproducible analysis results, while greatly reducing the work pressure of radiologists, and improving the diagnosis accuracy of breast cancer [10], [11].”
BackgroundContext Aware SmartHealth Cloud Platform for Medical Diagnostics
Shafqat, S., Abbasi, A., Naeem, M., Ahsan, M., Amjad, T., & Farooq, H. U. (2018) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2018.090741 · Cited by 9
“Google Cloud OLAP X BigQuer y HL7 Predictive Analytics X Classificatio n Model C4.5 Weka X ANFIS X ANFIS prediction Model Genfis3 MATLA B X Hierarchic al twotiered CADe CADe X Deep ConvNet s X X Medical Diagnostic System X X MLP neural network s MATLA B with NETLAB X PAPNET X Neural network model ANN X X 307 | P a g e…”
BackgroundMethodInfluentialHarchegani, H. B., & Moghaddasi, H. (2024) · International Journal of Preventive Medicine · doi:10.4103/ijpvm.ijpvm_373_22 · Cited by 7
AFA: adversarial frequency alignment for domain generalized lung nodule detection
Yin, B., Sun, M., Zhang, J., Liu, W., Liu, C., & Wang, Z. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-06928-9 · Cited by 7
“5D [43] and 3D [44] networks are introduced to automatically learn effective nodule features.”
BackgroundMulti Class Image Classification for Detection Of Diseases Using Chest X Ray Images
Choudhuri, R., & Paul, A. (2021) · International Conference on Computing for Sustainable Global Development · doi:10.1109/indiacom51348.2021.00137 · Cited by 7
“With limited quantity and variety of images, the biggest challenge in medical image diagnosis is to train the models well enough so that it doesn’t over fit on small data [8 - 10].”
BackgroundClassification of Diabetic Rat Histopathology Images Using Convolutional Neural Networks
Yurttakal, A., Erbay, H., Çinarer, G., & Baş, H. (2020) · International Journal of Computational Intelligence Systems · doi:10.2991/ijcis.d.201110.001 · Cited by 7
“Thus, successful studies have been performed in imaging pathology especially, CNN-based studies such as brain tumor diagnosis using MR images, interstitial lung disease diagnosis using CT images, and colon cancer diagnosis using histopathological images are some of the sounding ones [15,35,36].”
BackgroundPredicting Prodromal Dementia Using Linguistic Patterns and Deficits
Alkenani, A. H., Li, Y., Xu, Y., & Zhang, Q. (2020) · IEEE Access · doi:10.1109/access.2020.3029907 · Cited by 9
“In addition, a current out-of-control limitation is the sparse nature of related datasets, which happens to be a limitation across various computational diagnostic studies [83], [84].”
BackgroundKurniawan, E., Prajitno, P., & Soejoko, D. (2020) · Journal of Physics, Conference Series · doi:10.1088/1742-6596/1505/1/012018 · Cited by 7
Martinez, J. B., & Gill, G. (2019) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci49370.2019.00188 · Cited by 7
“Using a 2.5D dataset may also allow for better classification results since the disease may grow vertically along with the patient, not just horizontally [11].”
MethodA Review of Deep Learning Architectures and Their Application
Kamarudin, J. A. M., Abdullah, A., & Sallehuddin, R. S. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-6502-6_7 · Cited by 9
Guo, D., Ge, J., Yan, K., Wang, P., Zhu, Z., Zheng, D., Hua, X.-S., Lü, L., Ho, T., Ye, X., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16443-9_6 · Cited by 7
“Thoracic LN detection and segmentation has been exploited for more than a decade mainly focusing on extracting effective LN features, incorporating organ priors or utilizing advanced learning models [1–4, 7–9, 13–17, 25].”
MethodSelf-citationZhang, X., Lin, W.-M., Xiao, M., & Ji, H. (2021) · Electromagnetic waves · doi:10.2528/pier21051102 · Cited by 10
“patches were assigned to three channels to form a 48× 48× 3 patch [28], which we called a 2.”
MethodIacob, A. M., Fernández, M. C., Robledo, L. F., Castro, E. B., & Martínez, M. F. E. (2025) · Dentistry Journal · doi:10.3390/dj13090413 · Cited by 7
“To address this, augmentation procedures can be applied [35], which involve altering the dataset through transformations such as cropping, rotation, translation, zooming, elastic deformation, or changes in contrast or resolution [51].”
Wang, H., Ying, J., Liu, J., Yu, T., & Huang, D. (2024) · Therapeutics and Clinical Risk Management · doi:10.2147/tcrm.s483907 · Cited by 6
Self-citationA systematic review of deep learning-based spinal bone lesion detection in medical images
Teodorescu, B., Gilberg, L., Melton, P. W., Hehr, R. M., Güzel, H. E., Koç, A. M., Baumgart, A., Maerkisch, L., & Ataide, E. J. G. (2024) · Acta Radiologica · doi:10.1177/02841851241263066 · Cited by 6
“For the index test domain, we considered the concerns to be unclear in four cases ( 28,32,34,39 ) .”
InfluentialFMA-Net: Fusion of Multi-Scale Attention for Grading Cervical Precancerous Lesions
Duan, Z., Xu, C., Li, Z., Feng, B., & Nie, C. (2024) · Mathematics · doi:10.3390/math12070958 · Cited by 7
“In segmentation tasks, Ronneberger et al. proposed U-Net [8], a commonly used convolutional neural network structure widely applied in medical image segmentation tasks [9,10].”
MethodYin, H., Jiang, Y., Xu, Z., Huang, W., Chen, T., & Lin, G. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2021.805911 · Cited by 9
“The data augmentation strategy can help prevent network overfitting and avoid interference from various sources of noise to improve the robustness of the model (15, 16).”
BackgroundShivakumar, N., Chandrashekar, A., Handa, A. I., & Lee, R. (2021) · Postgraduate Medical Journal · doi:10.1136/postgradmedj-2020-139620 · Cited by 6
“23 Good accuracy of detection of various metastatic lesions is reported by many of the studies with area under the receiver operator characteristic curve (AUROC) greater than 0.9.”
BackgroundMethodInfluentialImpact of Artificial Intelligence in the field of Health Care
Ragavi, V., Sheela, A. C. S., & Kannaiyan, G. N. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1831/1/012006 · Cited by 10
“Deep neural network is able to detect enlarged lymph nodes in tomography images [17].”
BackgroundUsing explainable deep learning in da Vinci Xi robot for tumor detection
Azad, R. I., Mukhopadhyay, S., & Asadnia, M. (2021) · International Journal on Smart Sensing and Intelligent Systems · doi:10.21307/ijssis-2021-017 · Cited by 6
Application of Lightweight Convolution Neural Network in Cancer Diagnosis
Zhao, C., Feng, Y.-Y., Liu, R.-J., & Zheng, W. (2020) · Proceedings of the 2020 Conference on Artificial Intelligence and Healthcare · doi:10.1145/3433996.3434042 · Cited by 6
“After the development of convolutional neural network model, due to its excellent performance of traditional convolutional neural network model, it has been applied to various fields, such as automatic driving [2-3], behavior recognition [4], automatic speech recognition [5] and medical treatment [6-11].”
MethodTest Data Generation for False Data Injection Attack Testing in Air Traffic Surveillance
Cretin, A., Vernotte, A., Chevrot, A., Peureux, F., & Legeard, B. (2020) · IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW) · doi:10.1109/icstw50294.2020.00034 · Cited by 12
“, detecting abnormal cells or markers on medical imagery [16], [18], detecting intruders on a network using logging information [24], or detecting traffic inconsistencies in bus trajectory data [9].”
BackgroundKansal, S., Goel, S., Bhattacharya, J., & Srivastava, V. (2020) · Laser physics · doi:10.1088/1555-6611/abb596 · Cited by 6
“The total number of images, having applied the classical augmentation techniques given by equation (1) is as given in [24]:”
MethodLiver Guided Pancreas Segmentation
Zhang, Y., Wu, J., Wang, S., Liu, Y., Chen, Y.-F., Wu, E., & Tang, X.-Y. (2020) · IEEE International Symposium on Biomedical Imaging · doi:10.1109/isbi45749.2020.9098388 · Cited by 6
“5% in a 3D image) [2, 3].”
Wang, K., Zhang, X.-H., Huang, S., & Chen, F.-Y. (2019) · Chinese Conference on Pattern Recognition and Computer Vision · doi:10.1007/978-3-030-31723-2_28 · Cited by 6
Lymph node detection method based on multisource transfer learning and convolutional neural network
Ma, Y., & Peng, Y. (2019) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22371 · Cited by 6
Machine Learning Systems for Highly-Distributed and Rapidly-Growing Data
Hsieh, K. (2019) · arXiv.org · doi:10.1184/r1/10262450.v1 · Cited by 6
“ased on CNNs. 2) Bioinformatics and geoinformatics. Many bioinformatics and geoinformatics systems leverage CNNs to process a large dataset, such as anomaly classi•cation in biomedical imaging (e.g., [106,131]), information decoding in biomedical signal recordings (e.g., [145]), and pa−ern recognition in satellite ima…”
BackgroundTowards Automated Breast Mass Classification using Deep Learning Framework
Sarkar, P. R., Prabhakar, P., Mishra, D., & Subrahmanyam, G. (2019) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2019.00060 · Cited by 9
“We took 9 rotations for each training images ([0, 315] with 45 intervals) [30] and increased the training data size 9 times.”
MethodAutomatic Cervical Cell Classification Using Features Extracted by Convolutional Neural Network
Rohmatillah, M., Pramono, S. H., Rahmadwati, Suyono, H., & Sena, S. A. (2018) · Electrical Power, Electronics, Communications, Controls and Informatics Seminar (EECCIS) · doi:10.1109/eeccis.2018.8692888 · Cited by 8
“In order to overcome this issue, many researches have been developed methods [2], [3], [4], [5] to help doctors in making better decision to prevent more severe condition.”
MethodDeep Medical Image Computing in Preventive and Precision Medicine
Lu, L., & Harrison, A. P. (2018) · IEEE Multimedia · doi:10.1109/mmul.2018.2875861 · Cited by 6
Self-citationChmelík, J., Jakubícek, R., Jan, J., Ourednicek, P., Lambert, L., Amadori, E., & Gavelli, G. (2018) · IFMBE Proceedings · doi:10.1007/978-981-10-9035-6_28 · Cited by 6
Lü, L., Wu, D., Lay, N. S., Liu, D., Nogues, I., & Summers, R. M. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477606 · Cited by 5
“Applying a 3D regional CNN [17, 19] to our dataset is infeasible, due to a lack of training data and of a good quality pre-trained model for adaption and fine-tuning.”
BackgroundMethodSelf-citationMultimodal medical volumes translation and segmentation with generative adversarial network
Zhang, Z., Yang, L., & Zheng, Y. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-816176-0.00013-2 · Cited by 4
Roth, H. R., Lü, L., Liu, J., Yao, J., Seff, A., Cherry, K. M., Kim, L., & Summers, R. M. (2017) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-42999-1_3 · Cited by 8
Self-citationUnsupervised generative learning-based decision-making system for COVID-19 detection
Menon, N., Yadav, P., Ravi, V., Acharya, V., & Sowmya, V. (2024) · Health and Technology · doi:10.1007/s12553-024-00879-y · Cited by 5
“However, as noted in prior research like [13, 14], the amount and variety of data that may be used to train supervised learning models in the field of medical imaging is constrained.”
U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers
Alsrehin, N. O., Gupta, M., Alsmadi, I., & Alrababah, S. A. (2023) · Applied Sciences · doi:10.3390/app132111898 · Cited by 5
Wang, Y., Jeong, W. G., Zhang, H., Choi, Y., Jin, G.-Y., & Ko, S.-B. (2023) · Multimedia tools and applications · doi:10.1007/s11042-023-17210-y · Cited by 5
Huang, H., Xie, Y., Wang, G., Zhang, L., & Zhou, W. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107201 · Cited by 5
CT manifestations of gallbladder carcinoma based on neural network
Chang, Y.-G., Wu, Q., Chi, L., & Huo, H.-Y. (2022) · Neural computing & applications (Print) · doi:10.1007/s00521-022-06973-4 · Cited by 5
“The probability of actually being sick and being diagnosed as positive is sensitivity (sensitivity, Sen), namely [7]: Sen 1⁄4 P T D j ð Þ 1⁄4 TP= TPþ FN ð Þ ð1Þ”
Zhong, Y., Bi, T.-Q., Wang, J., Wu, S., Jiang, T., & Huang, Y. (2021) · Ad hoc networks · doi:10.1016/j.adhoc.2021.102438 · Cited by 5
Metadata
- Authors
- Roth, H. R., Lu, L., Liu, J., Yao, J., Seff, A., Cherry, K., Kim, L., & Summers, R. M.
- Affiliations
- National Institutes of Health Clinical Center (US)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2016-05
- Volume
- 35
- Issue
- 5
- Pages
- 1170-1181
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- PMC
- PMC7340334
- OpenAlex
- W1871050032
- Cited by
- 608
- References
- 60
- Citations by year
- 2026: 14 · 2025: 19 · 2024: 35 · 2023: 34 · 2022: 72 · 2021: 101 · 2020: 88 · 2019: 84 · 2018: 71 · 2017: 62 · 2016: 27
- FWCI
- 52.62
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (public-domain)
- Funders
- National Institutes of Health
- NIH Clinical Center (Z01CL040004, Z01CL040003)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- computer-aided detection, false positive reduction, convolutional neural networks, lymph node detection, colorectal polyp detection, scale transformation
- MeSH terms
- Machine Learning, Adolescent, Adult, Aged, Child, Colonic Polyps, Female, Humans, Lymph Nodes, Male, Middle Aged, Radiographic Image Interpretation, Computer-Assisted, Spinal Neoplasms, Tomography, X-Ray Computed, Databases, Factual, Neural Networks, Computer, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
